🧠 Autonomous Research Agent

This is an AI-powered Flask application that:

• Uses Groq's LLaMA3 (via llama-3.3-70b-versatile) and Tavily Search to research any topic.
• Generates a blog article with LangChain agents.
• Exports to PDF and saves locally (previously Notion, now output/ directory).

🔧 Setup

1. Clone the repository:

   git clone https://github.com/sudarshanmestha/autonomous-research-ai.git
   cd autonomous-research-ai

2. Set up a virtual environment:

python -m venv venv && source venv/bin/activate

3. Install dependencies:

pip install -r requirements.txt

4. Create a .env file with your API keys:

GROQ_API_KEY=gsk_your_groq_key
TAVILY_API_KEY=tvly_your_tavily_key
NOTION_API_KEY=...
NOTION_DB_ID=...

quick start

1. source venv/bin/activate
   python app.py
2. Open http://127.0.0.1:8080 in your browser.
3. Enter a topic (e.g., "AI in 2025") and click "Generate" to create a blog.

📝 Usage Examples

1. Research Agent

The run_researcher_agent function fetches and summarizes research:

from agents.researcher_agent import run_researcher_agent
research = run_researcher_agent("AI in 2025")
print(research)  # Outputs summarized research content

Uses Tavily Search for web data and Groq LLM for summarization.

2. Writer Agent

The generate_blog function creates an article:

from agents.writer_agent import generate_blog
article = generate_blog(research)
print(article)  # Outputs a formatted blog (e.g., # Title, ## Section)

💾 Local Storage

Generated articles are saved as .md and .pdf files in the output/ directory.
Example filename: output/AI_in_2025_20250930_1910.md.
Check this folder after generating to access your files.

🛠️ Troubleshooting

Port Conflict (8080): If "Address already in use", kill the process:

sudo lsof -i :8080
sudo kill -9 <PID>

API Errors: Ensure GROQ_API_KEY and TAVILY_API_KEY are valid; check quotas at console.groq.com and tavily.com.
PDF Issues: Verify wkhtmltopdf is installed (wkhtmltopdf --version).